Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
This work addresses the need for standardized evaluation and realistic data in multi-camera tracking, though it is incremental as it builds on existing tracking methods.
The paper tackles the problem of evaluating multi-target, multi-camera tracking systems by introducing new performance measures and a large annotated dataset, resulting in over 2 million frames of video with 2,700 identities to benchmark trackers.
To help accelerate progress in multi-target, multi-camera tracking systems, we present (i) a new pair of precision-recall measures of performance that treats errors of all types uniformly and emphasizes correct identification over sources of error; (ii) the largest fully-annotated and calibrated data set to date with more than 2 million frames of 1080p, 60fps video taken by 8 cameras observing more than 2,700 identities over 85 minutes; and (iii) a reference software system as a comparison baseline. We show that (i) our measures properly account for bottom-line identity match performance in the multi-camera setting; (ii) our data set poses realistic challenges to current trackers; and (iii) the performance of our system is comparable to the state of the art.